INDEX

Explanations

names and phrases in Spanish starting with "es"

oai_token-act-pair · gpt-3.5-turbo

repeated instances of the word "es" and its variations in Spanish text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CPC

-0.71

DragonMagazine

-0.68

 Grimes

-0.64

 IMAGES

-0.63

 Hide

-0.62

 Kubrick

-0.62

ASC

-0.60

 McCartney

-0.59

éĸ

-0.58

CMS

-0.57

POSITIVE LOGITS

oteric

1.25

earchers

1.14

quire

1.14

earch

1.11

ports

1.07

terday

1.07

pect

1.04

ylum

0.97

sembly

0.97

pected

0.97

Activations Density 0.024%

names and phrases in Spanish starting with "es"

repeated instances of the word "es" and its variations in Spanish text

No Comments

No Known Activations